© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108297
    Prev
    Next
    INDEX
    Explanations

    export default class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     también
    -0.90
     nena
    -0.84
     also
    -0.84
    chke
    -0.81
     złota
    -0.79
    жества
    -0.77
     Very
    -0.77
     svært
    -0.77
     on
    -0.75
     just
    -0.75
    POSITIVE LOGITS
    static
    1.50
    async
    1.38
     async
    1.38
     static
    1.25
     atentos
    1.00
    Taco
    0.98
    VPS
    0.97
    Literat
    0.94
     alleine
    0.91
    靜
    0.91
    Activations Density 0.008%

    No Known Activations